paper-with-me

Papers

Sublinear Optimal Policy Value Estimation in Contextual Bandits

2019-12-12 · Weihao Kong, Gregory Valiant, Emma Brunskill

We study the problem of estimating the expected reward of the optimal policy in the stochastic disjoint linear bandit setting. We prove that for certain settings it is possible to obtain an accurate estimate of the optimal policy value even with a number of samples that is sublinear in the number that would be required to \emph{find} a policy that realizes a value close to this optima. We establish nearly matching information theoretic lower bounds, showing that our algorithm achieves near optimal estimation error. Finally, we demonstrate the effectiveness of our algorithm on joke recommendation and cancer inhibition dosage selection problems using real datasets.

📄 PDF Abstract BibTeX arXiv:1912.06111

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed Bandits

Similar Papers 제목 키워드 기반

Estimating Optimal Policy Value in General Linear Contextual Bandits

2023-02-19 · Jonathan N. Lee, Weihao Kong, Aldo Pacchiano, Vidya Muthukumar 외

In many bandit problems, the maximal reward achievable by a policy is often unknown in advance. We consider the problem of estimating the optimal policy value in the sublinear data regime before the optimal policy is eve…

Model SelectionMulti-Armed Bandits

$α$-Fair Contextual Bandits

2023-10-22 · Siddhant Chaudhary, Abhishek Sinha

Contextual bandit algorithms are at the core of many applications, including recommender systems, clinical trials, and optimal portfolio selection. One of the most popular problems studied in the contextual bandit litera…

Multi-Armed BanditsRecommendation Systems

Provably Efficient Lifelong Reinforcement Learning with Linear Function Approximation

2022-06-01 · Sanae Amani, Lin F. Yang, Ching-An Cheng

We study lifelong reinforcement learning (RL) in a regret minimization setting of linear contextual Markov decision process (MDP), where the agent needs to learn a multi-task policy while solving a streaming sequence of …

4kLifelong learningreinforcement-learningReinforcement Learning+1

Learning Kernel-Based MDPs from Episodic Preferential Feedback

2026-05-22 · Nikola Pavlovic, Sattar Vakili, Qing Zhao arxiv

Human feedback often arrives as preferences rather than calibrated numeric rewards, motivating reinforcement learning from preferential feedback, also referred to as reinforcement learning from human feedback (RLHF). We …

Reinforcement Learning

Best of Both Worlds in Online Control: Competitive Ratio and Policy Regret

2022-11-21 · Gautam Goel, Naman Agarwal, Karan Singh, Elad Hazan

We consider the fundamental problem of online control of a linear dynamical system from two different viewpoints: regret minimization and competitive analysis. We prove that the optimal competitive policy is well-approxi…